> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://www.comet.com/docs/opik/reference/rest-api/traces/get-traces-by-project/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://www.comet.com/_mcp/server.

# Get traces by project_name or project_id

GET http://localhost:5173/api/v1/private/traces

Get traces by project_name or project_id

Reference: https://www.comet.com/docs/opik/reference/rest-api/traces/get-traces-by-project

## Servers

- `http://localhost:5173/api` (Local server, default)
- `https://www.comet.com/opik/api` (Opik Cloud)

## Request

### Query parameters

- `page` (integer, optional, default: 1)
- `size` (integer, optional, default: 10)
- `project_name` (string, optional)
- `project_id` (string, optional)
- `filters` (string, optional)
- `truncate` (boolean, optional, default: false)
- `strip_attachments` (boolean, optional, default: false)
- `sorting` (string, optional)
- `exclude` (string, optional)
- `search` (string, optional)
- `from_time` (datetime, optional)
- `to_time` (datetime, optional)
- `annotation_queue_id` (string, optional)

## Response

### 200

Trace resource

- `page` (integer, optional)
- `size` (integer, optional)
- `total` (long, optional)
- `content` (list of Trace_Public, optional)
- `sortableBy` (list of string, optional)

## Types

### Trace_Public

- `start_time` (datetime, required)
- `id` (string, optional)
- `project_id` (string, optional)
- `name` (string, optional)
- `end_time` (datetime, optional)
- `input` (JsonListString_Public, optional)
- `output` (JsonListString_Public, optional)
- `metadata` (JsonListString_Public, optional)
- `tags` (list of string, optional)
- `error_info` (ErrorInfo_Public, optional)
- `usage` (map from string to long, optional)
- `created_at` (datetime, optional)
- `last_updated_at` (datetime, optional)
- `created_by` (string, optional)
- `last_updated_by` (string, optional)
- `feedback_scores` (list of FeedbackScore_Public, optional)
- `span_feedback_scores` (list of FeedbackScore_Public, optional) — Aggregated feedback scores from all spans in this trace, averaged by score name
- `comments` (list of Comment_Public, optional)
- `guardrails_validations` (list of GuardrailsValidation_Public, optional)
- `total_estimated_cost` (double, optional)
- `span_count` (integer, optional)
- `duration` (double, optional) — Duration in milliseconds as a decimal number to support sub-millisecond precision
- `ttft` (double, optional) — Time to first token in milliseconds
- `thread_id` (string, optional)
- `visibility_mode` (enum, optional)
  - Allowed values: `default`, `hidden`
- `llm_span_count` (integer, optional)
- `has_tool_spans` (boolean, optional)
- `providers` (list of string, optional) — List of unique provider names from all spans in this trace, sorted alphabetically
- `experiment` (ExperimentItemReference_Public, optional) — Experiment reference with ID, name, dataset ID, and dataset item ID
- `annotation_queues` (list of AnnotationQueueReference_Public, optional) — Annotation queues this trace is currently an item of
- `source` (enum, optional)
  - Allowed values: `sdk`, `experiment`, `playground`, `optimization`, `evaluator`
- `environment` (string, optional)

### JsonListString_Public

### ErrorInfo_Public

- `exception_type` (string, required)
- `traceback` (string, required)
- `message` (string, optional)

### FeedbackScore_Public

Aggregated feedback scores from all spans in this trace, averaged by score name

- `name` (string, required)
- `value` (double, required)
- `source` (enum, required)
  - Allowed values: `ui`, `sdk`, `online_scoring`
- `category_name` (string, optional)
- `reason` (string, optional)
- `source_queue_id` (string, optional)
- `created_at` (datetime, optional)
- `last_updated_at` (datetime, optional)
- `created_by` (string, optional)
- `last_updated_by` (string, optional)
- `value_by_author` (map from string to ValueEntry_Public, optional)

### Comment_Public

- `text` (string, required)
- `id` (string, optional)
- `source_queue_id` (string, optional)
- `created_at` (datetime, optional)
- `last_updated_at` (datetime, optional)
- `created_by` (string, optional)
- `last_updated_by` (string, optional)

### GuardrailsValidation_Public

- `span_id` (string, optional)
- `checks` (list of Check_Public, optional)

### ExperimentItemReference_Public

Experiment reference with ID, name, dataset ID, and dataset item ID

- `id` (string, required) — Experiment ID
- `name` (string, required) — Experiment name
- `dataset_id` (string, required) — Dataset ID
- `dataset_item_id` (string, required) — Dataset Item ID

### AnnotationQueueReference_Public

Annotation queue reference with ID and name

- `id` (string, required) — Annotation queue ID
- `name` (string, required) — Annotation queue name

### ValueEntry_Public

- `value` (double, optional)
- `reason` (string, optional)
- `category_name` (string, optional)
- `source` (enum, optional)
  - Allowed values: `ui`, `sdk`, `online_scoring`
- `last_updated_at` (datetime, optional)
- `span_type` (string, optional)
- `span_id` (string, optional)
- `source_queue_id` (string, optional)
- `author` (string, optional)

### Check_Public

- `name` (enum, optional)
  - Allowed values: `TOPIC`, `PII`, `LLM_JUDGE`, `PROMPT_INJECTION`, `CUSTOM_CLASSIFIER`
- `result` (enum, optional)
  - Allowed values: `passed`, `failed`

## Examples

**Response**

```json
{
  "page": 1,
  "size": 1,
  "total": 1,
  "content": [
    {
      "start_time": "2024-01-15T09:30:00Z",
      "id": "string",
      "project_id": "string",
      "name": "string",
      "end_time": "2024-01-15T09:30:00Z",
      "input": {},
      "output": {},
      "metadata": {},
      "tags": [
        "string"
      ],
      "error_info": {
        "exception_type": "string",
        "traceback": "string",
        "message": "string"
      },
      "usage": {},
      "created_at": "2024-01-15T09:30:00Z",
      "last_updated_at": "2024-01-15T09:30:00Z",
      "created_by": "string",
      "last_updated_by": "string",
      "feedback_scores": [
        {
          "name": "string",
          "value": 1.1,
          "source": "ui",
          "category_name": "string",
          "reason": "string",
          "source_queue_id": "string",
          "created_at": "2024-01-15T09:30:00Z",
          "last_updated_at": "2024-01-15T09:30:00Z",
          "created_by": "string",
          "last_updated_by": "string",
          "value_by_author": {}
        }
      ],
      "span_feedback_scores": [
        {
          "name": "string",
          "value": 1.1,
          "source": "ui",
          "category_name": "string",
          "reason": "string",
          "source_queue_id": "string",
          "created_at": "2024-01-15T09:30:00Z",
          "last_updated_at": "2024-01-15T09:30:00Z",
          "created_by": "string",
          "last_updated_by": "string",
          "value_by_author": {}
        }
      ],
      "comments": [
        {
          "text": "string",
          "id": "string",
          "source_queue_id": "string",
          "created_at": "2024-01-15T09:30:00Z",
          "last_updated_at": "2024-01-15T09:30:00Z",
          "created_by": "string",
          "last_updated_by": "string"
        }
      ],
      "guardrails_validations": [
        {
          "span_id": "string",
          "checks": [
            {
              "name": "TOPIC",
              "result": "passed"
            }
          ]
        }
      ],
      "total_estimated_cost": 1.1,
      "span_count": 1,
      "duration": 1.1,
      "ttft": 1.1,
      "thread_id": "string",
      "visibility_mode": "default",
      "llm_span_count": 1,
      "has_tool_spans": true,
      "providers": [
        "string"
      ],
      "experiment": {
        "id": "string",
        "name": "string",
        "dataset_id": "string",
        "dataset_item_id": "string"
      },
      "annotation_queues": [
        {
          "id": "string",
          "name": "string"
        }
      ],
      "source": "sdk",
      "environment": "string"
    }
  ],
  "sortableBy": [
    "string"
  ]
}
```

**SDK Code**

```python
import requests

url = "http://localhost:5173/api/v1/private/traces"

response = requests.get(url)

print(response.json())
```

```javascript
const url = 'http://localhost:5173/api/v1/private/traces';
const options = {method: 'GET'};

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}
```

```go
package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "http://localhost:5173/api/v1/private/traces"

	req, _ := http.NewRequest("GET", url, nil)

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(res)
	fmt.Println(string(body))

}
```

```ruby
require 'uri'
require 'net/http'

url = URI("http://localhost:5173/api/v1/private/traces")

http = Net::HTTP.new(url.host, url.port)

request = Net::HTTP::Get.new(url)

response = http.request(request)
puts response.read_body
```

```java
import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.Unirest;

HttpResponse<String> response = Unirest.get("http://localhost:5173/api/v1/private/traces")
  .asString();
```

```php
<?php
require_once('vendor/autoload.php');

$client = new \GuzzleHttp\Client();

$response = $client->request('GET', 'http://localhost:5173/api/v1/private/traces');

echo $response->getBody();
```

```csharp
using RestSharp;

var client = new RestClient("http://localhost:5173/api/v1/private/traces");
var request = new RestRequest(Method.GET);
IRestResponse response = client.Execute(request);
```

```swift
import Foundation

let request = NSMutableURLRequest(url: NSURL(string: "http://localhost:5173/api/v1/private/traces")! as URL,
                                        cachePolicy: .useProtocolCachePolicy,
                                    timeoutInterval: 10.0)
request.httpMethod = "GET"

let session = URLSession.shared
let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in
  if (error != nil) {
    print(error as Any)
  } else {
    let httpResponse = response as? HTTPURLResponse
    print(httpResponse)
  }
})

dataTask.resume()
```

> Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.